Never Type Again
Speak Naturally. Write Instantly. Stay Private.
FluidVoice is a native macOS app: trigger it, speak naturally, and text appears in Notes, Slack, Cursor, Gmail, or any text field. Local AI keeps your voice on-device. Free forever.
25,000+ downloads and counting
Built with FluidAudio for fast local transcription.
See FluidVoice in action
Fast, accurate speech-to-text wherever you type.
Quick facts
Source-aligned FluidVoice details
Platform
macOS 15.0 Sequoia or later
Hardware
Apple Silicon; Intel supported from 1.5.1 builds using Whisper
Price
Free
License
GPLv3 from 2026-02-23 onward
Primary models
Parakeet Flash, Parakeet TDT v3/v2, Cohere Transcribe, Apple Speech, Whisper
Privacy
Local-first; optional anonymous analytics; optional AI provider keys stored in macOS Keychain
Speed, in plain terms
Speaking is ~3.7× faster than typing
At 500 words, that’s about 9 minutes saved — and you stay in flow while your hands do something else.
Feels instant
Low-latency, on-device transcription that keeps up with you.
Works everywhere
Any text field: docs, email, chat, and code.
Stays private
No cloud uploads — your voice stays on your Mac.
Community proof from real workflows
Direct feedback from developers, multilingual users, and early adopters who switched from typing-heavy workflows.
Free forever
"Thank you for making it free, forever! Hope to see it support more languages soon!"
GitHub discussion
Community-first growth
"Very nice! I imagine monetization in future might be easier cause you're being distributed for free. Smart plan. Hoping you get a big following and base!"
Early adopter feedback
Open source trust
"Thanks for making it open source"
Developer comment
Multilingual reliability
"Thank you so much. It works fine in German by the way (Tahoe, Mac Mini M2 Pro, external mic). This opens a host of new possibilities for interacting with my Mac while avoiding typing, which I'm very slow at. I am really excited. No AI post-processing yet for me."
German workflow
Intent recovery
"Wow, impressive. I stumbled while dictating and the transcriber caught it and output the word I had intended to say!"
Daily dictation
Head-to-head speed
"This is a really impressive app, speedy and accurate. It's just as good as Wispr Flow in my testing"
Comparison test
Product polish
"This is unbelievably slick. Congrats, and well done."
Launch feedback
Open source goodwill
"Solid product! and super cool of you to make it open source :)"
Community comment
Language + media
"I just did a quick test in French using dictation and also tried transcribing a video — both worked very well."
French test
Developer adoption
"Love the project. Thanks for building this!"
GitHub reaction
Retention
"Having been one of the early users, I want to say thank you and amazing job!"
Early user
Momentum
"All the best of success with this. Congrats :)"
Community support
Free forever
"Thank you for making it free, forever! Hope to see it support more languages soon!"
GitHub discussion
Community-first growth
"Very nice! I imagine monetization in future might be easier cause you're being distributed for free. Smart plan. Hoping you get a big following and base!"
Early adopter feedback
Open source trust
"Thanks for making it open source"
Developer comment
Multilingual reliability
"Thank you so much. It works fine in German by the way (Tahoe, Mac Mini M2 Pro, external mic). This opens a host of new possibilities for interacting with my Mac while avoiding typing, which I'm very slow at. I am really excited. No AI post-processing yet for me."
German workflow
Intent recovery
"Wow, impressive. I stumbled while dictating and the transcriber caught it and output the word I had intended to say!"
Daily dictation
Head-to-head speed
"This is a really impressive app, speedy and accurate. It's just as good as Wispr Flow in my testing"
Comparison test
Product polish
"This is unbelievably slick. Congrats, and well done."
Launch feedback
Open source goodwill
"Solid product! and super cool of you to make it open source :)"
Community comment
Language + media
"I just did a quick test in French using dictation and also tried transcribing a video — both worked very well."
French test
Developer adoption
"Love the project. Thanks for building this!"
GitHub reaction
Retention
"Having been one of the early users, I want to say thank you and amazing job!"
Early user
Momentum
"All the best of success with this. Congrats :)"
Community support
Why teams choose FluidVoice
Built to remove typing friction without giving up privacy, performance, or control.
Private by default. Free forever.
FluidVoice is local-first, avoids recurring subscription costs, and stays transparent through open source code.
Local speech models process dictation on your Mac
Optional AI provider keys are stored in macOS Keychain
GPLv3 source you can inspect and extend
~3.7x faster than typing
Real-time response
Speak naturally and see text land instantly, so ideas stay in motion.
System-wide input
Works in every text field
Email, docs, terminals, chat, and code editors all work with the same shortcut.
You control the final output
AI post-processing on demand
Keep raw dictation when you want speed, or clean phrasing with optional enhancement.
Parakeet v3 + Cohere + Whisper
Built for multilingual teams
Choose model-specific language coverage, from 25-language Parakeet TDT v3 to Cohere Transcribe and Whisper's broad compatibility.
Modes that adapt to your workflow
Switch context instantly instead of forcing one rigid dictation flow across every app and task.
Performance profile
Built for speed you can feel in real work
FluidVoice keeps inference local and latency low so your writing flow stays uninterrupted across long sessions.
Apple Silicon acceleration
CoreML and Metal deliver low-latency transcription while preserving battery efficiency.
Intel Macs support
OpenAI Whisper support keeps performance reliable on older Intel Macs.
System-wide behavior
One shortcut, any text field, no mode-switching overhead between tools.
3,380x
Real-time factor
Processes 56 minutes of speech in roughly one second.
<100ms
Perceived latency
Fast enough to feel immediate while moving through thought-heavy tasks.
Local
Local-first dictation
Local speech models keep dictation on-device; optional AI providers are user-controlled.
24 min
Single-pass limit
Handles long-form transcription windows without manual chunking.
Architecture highlights
Model lineup spans Parakeet Flash, Parakeet TDT v3/v2, Cohere Transcribe, Apple Speech, and Whisper, with optimized routing to keep transcription responsive across short bursts and long dictation sessions.
FAQ
Answers for teams evaluating voice-first workflows
These are the most common questions from users moving from typing-heavy workflows to local, always-available dictation.
Free forever, no paid tiers
Works across docs, chat, code, and terminal
On-device privacy by design